News for hackers. Stuff that matters.
Re:Human coders are still better than LLMs by all2 on Thursday May 29, 2025 @09:21PM (#44131905)
I don't cajole the model to do it. I rarely use what the model generates. I typically do my own thing after making an assessment of what the model writes. I orient myself in the problem space with the model, then use my knowledge to write a more concise solution.

There are no comments on this comment yet.